# Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection

arXiv: https://arxiv.org/abs/2412.20455 · HTML: https://mlsanity.com/paper/2412.20455/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 29 Dec 2024.

## Builds on (most cited first, 18 of 18)

- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Adversarially Learned One-Class Classifier for Novelty Detection](https://mlsanity.com/paper/1802.09088/) (2018)
- [Fully Hyperbolic Neural Networks](https://mlsanity.com/paper/2105.14686/) (2021)
- [Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2302.05160/) (2023)
- [W-TALC: Weakly-supervised Temporal Activity Localization and Classification](https://mlsanity.com/paper/1807.10418/) (2018)
- [Cross-Modality Fusion Transformer for Multispectral Object Detection](https://mlsanity.com/paper/2111.00273/) (2021)
- [Hyperbolic Graph Attention Network](https://mlsanity.com/paper/1912.03046/) (2019)
- [Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2212.04090/) (2022)
- [Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection](https://mlsanity.com/paper/2207.05500/) (2022)
- [Learning Weakly Supervised Audio-Visual Violence Detection in Hyperbolic Space](https://mlsanity.com/paper/2305.18797/) (2023)
- [Overlooked Video Classification in Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2210.06688/) (2022)
- [Pornographic Image Recognition via Weighted Multiple Instance Learning](https://mlsanity.com/paper/1902.03771/) (2019)
- [Hyperbolic Convolution via Kernel Point Aggregation](https://mlsanity.com/paper/2306.08862/) (2023)

## Built on by (most cited first, 10 of 10)

- [The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM](https://mlsanity.com/paper/2507.21649/) (2025)
- [LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention](https://mlsanity.com/paper/2506.02083/) (2025)
- [Uncertainty-Weighted Fusion of Image and Synthetic Event for Video Anomaly Detection](https://mlsanity.com/paper/2505.02393/) (2025)
- [Dual-Stream Alignment for Action Segmentation](https://mlsanity.com/paper/2510.07652/) (2025)
- [PiercingEye: Dual-Space Video Violence Detection with Hyperbolic Vision-Language Guidance](https://mlsanity.com/paper/2504.18866/) (2025)
- [DAMS:Dual-Branch Adaptive Multiscale Spatiotemporal Framework for Video Anomaly Detection](https://mlsanity.com/paper/2507.20629/) (2025)
- [RobustA: Robust Anomaly Detection in Multimodal Data](https://mlsanity.com/paper/2511.07276/) (2025)
- [3D Human-Human Interaction Anomaly Detection](https://mlsanity.com/paper/2512.13560/) (2025)
- [Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluated](https://mlsanity.com/paper/2608.21854/) (2026)
- [Multi-Modal Anomaly Detection: A Survey](https://mlsanity.com/paper/2608.24937/) (2026)

## Abstract (arXiv)

Recently, weakly supervised video anomaly detection (WS-VAD) has emerged as a contemporary research direction to identify anomaly events like violence and nudity in videos using only video-level labels. However, this task has substantial challenges, including addressing imbalanced modality information and consistently distinguishing between normal and abnormal features. In this paper, we address these challenges and propose a multi-modal WS-VAD framework to accurately detect anomalies such as violence and nudity. Within the proposed framework, we introduce a new fusion mechanism known as the Cross-modal Fusion Adapter (CFA), which dynamically selects and enhances highly relevant audio-visual features in relation to the visual modality. Additionally, we introduce a Hyperbolic Lorentzian Graph Attention (HLGAtt) to effectively capture the hierarchical relationships between normal and abnormal representations, thereby enhancing feature separation accuracy. Through extensive experiments, we demonstrate that the proposed model achieves state-of-the-art results on benchmark datasets of violence and nudity detection.